Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 462 insertions, 0 deletions

diff --git a/io_uring/memmap.c b/io_uring/memmap.c
new file mode 100644
index 000000000..48c0eb012
--- /dev/null
+++ b/io_uring/memmap.c
@@ -0,0 +1,462 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/io_uring.h>
+#include <linux/io_uring_types.h>
+#include <asm/shmparam.h>
+
+#include "memmap.h"
+#include "kbuf.h"
+#include "rsrc.h"
+#include "zcrx.h"
+
+static bool io_mem_alloc_compound(struct page **pages, int nr_pages,
+				  size_t size, gfp_t gfp,
+				  struct user_struct *user)
+{
+	unsigned long nr_compound, extra;
+	struct page *page;
+	int i, order;
+
+	order = get_order(size);
+	if (order > MAX_PAGE_ORDER)
+		return false;
+	else if (order)
+		gfp |= __GFP_COMP;
+
+	/*
+	 * get_order() rounds a non power of two size up, so the allocation
+	 * can hold more pages than the region exposes. Account those too,
+	 * and leave the compound allocation alone if they do not fit.
+	 */
+	nr_compound = 1UL << order;
+	extra = nr_compound - nr_pages;
+	if (extra && user && __io_account_mem(user, extra))
+		return false;
+
+	page = alloc_pages(gfp, order);
+	if (!page) {
+		if (extra && user)
+			__io_unaccount_mem(user, extra);
+		return false;
+	}
+
+	for (i = 0; i < nr_pages; i++)
+		pages[i] = page + i;
+
+	return true;
+}
+
+struct page **io_pin_pages(unsigned long uaddr, unsigned long len, int *npages)
+{
+	unsigned long start, end, nr_pages;
+	struct page **pages;
+	int ret;
+
+	if (check_add_overflow(uaddr, len, &end))
+		return ERR_PTR(-EOVERFLOW);
+	if (check_add_overflow(end, PAGE_SIZE - 1, &end))
+		return ERR_PTR(-EOVERFLOW);
+
+	end = end >> PAGE_SHIFT;
+	start = uaddr >> PAGE_SHIFT;
+	nr_pages = end - start;
+	if (WARN_ON_ONCE(!nr_pages))
+		return ERR_PTR(-EINVAL);
+	if (nr_pages > INT_MAX / sizeof(struct page *))
+		return ERR_PTR(-EOVERFLOW);
+
+	pages = kvmalloc_objs(struct page *, nr_pages, GFP_KERNEL_ACCOUNT);
+	if (!pages)
+		return ERR_PTR(-ENOMEM);
+
+	ret = pin_user_pages_fast(uaddr, nr_pages, FOLL_WRITE | FOLL_LONGTERM,
+					pages);
+	/* success, mapped all pages */
+	if (ret == nr_pages) {
+		*npages = nr_pages;
+		return pages;
+	}
+
+	/* partial map, or didn't map anything */
+	if (ret >= 0) {
+		/* if we did partial map, release any pages we did get */
+		if (ret)
+			unpin_user_pages(pages, ret);
+		ret = -EFAULT;
+	}
+	kvfree(pages);
+	return ERR_PTR(ret);
+}
+
+enum {
+	/* memory was vmap'ed for the kernel, freeing the region vunmap's it */
+	IO_REGION_F_VMAP			= 1,
+	/* memory is provided by user and pinned by the kernel */
+	IO_REGION_F_USER_PROVIDED		= 2,
+	/* only the first page in the array is ref'ed */
+	IO_REGION_F_SINGLE_REF			= 4,
+};
+
+void io_free_region(struct user_struct *user, struct io_mapped_region *mr)
+{
+	if (mr->pages) {
+		long nr_refs = mr->nr_pages;
+
+		if (mr->flags & IO_REGION_F_SINGLE_REF)
+			nr_refs = 1;
+
+		if (mr->flags & IO_REGION_F_USER_PROVIDED)
+			unpin_user_pages(mr->pages, nr_refs);
+		else
+			release_pages(mr->pages, nr_refs);
+
+		kvfree(mr->pages);
+	}
+	if ((mr->flags & IO_REGION_F_VMAP) && mr->ptr)
+		vunmap(mr->ptr);
+	if (mr->nr_pages && user) {
+		unsigned long nr_accounted = mr->nr_pages;
+
+		/* a compound region was accounted for the whole allocation */
+		if (mr->flags & IO_REGION_F_SINGLE_REF)
+			nr_accounted = 1UL << get_order(io_region_size(mr));
+
+		__io_unaccount_mem(user, nr_accounted);
+	}
+
+	memset(mr, 0, sizeof(*mr));
+}
+
+static int io_region_init_ptr(struct io_mapped_region *mr)
+{
+	struct io_imu_folio_data ifd;
+	void *ptr;
+
+	if (io_check_coalesce_buffer(mr->pages, mr->nr_pages, &ifd)) {
+		if (ifd.nr_folios == 1 && !PageHighMem(mr->pages[0])) {
+			mr->ptr = page_address(mr->pages[0]);
+			return 0;
+		}
+	}
+	ptr = vmap(mr->pages, mr->nr_pages, VM_MAP, PAGE_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	mr->ptr = ptr;
+	mr->flags |= IO_REGION_F_VMAP;
+	return 0;
+}
+
+static int io_region_pin_pages(struct io_mapped_region *mr,
+			       struct io_uring_region_desc *reg)
+{
+	size_t size = io_region_size(mr);
+	struct page **pages;
+	int nr_pages;
+
+	pages = io_pin_pages(reg->user_addr, size, &nr_pages);
+	if (IS_ERR(pages))
+		return PTR_ERR(pages);
+	if (WARN_ON_ONCE(nr_pages != mr->nr_pages))
+		return -EFAULT;
+
+	mr->pages = pages;
+	mr->flags |= IO_REGION_F_USER_PROVIDED;
+	return 0;
+}
+
+static int io_region_allocate_pages(struct io_mapped_region *mr,
+				    struct io_uring_region_desc *reg,
+				    unsigned long mmap_offset,
+				    struct user_struct *user)
+{
+	gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN;
+	size_t size = io_region_size(mr);
+	unsigned long nr_allocated;
+	struct page **pages;
+
+	pages = kvmalloc_objs(*pages, mr->nr_pages, gfp);
+	if (!pages)
+		return -ENOMEM;
+
+	if (io_mem_alloc_compound(pages, mr->nr_pages, size, gfp, user)) {
+		mr->flags |= IO_REGION_F_SINGLE_REF;
+		goto done;
+	}
+
+	nr_allocated = alloc_pages_bulk_node(gfp, NUMA_NO_NODE,
+					     mr->nr_pages, pages);
+	if (nr_allocated != mr->nr_pages) {
+		if (nr_allocated)
+			release_pages(pages, nr_allocated);
+		kvfree(pages);
+		return -ENOMEM;
+	}
+done:
+	reg->mmap_offset = mmap_offset;
+	mr->pages = pages;
+	return 0;
+}
+
+int io_create_region(struct io_ring_ctx *ctx, struct io_mapped_region *mr,
+		     struct io_uring_region_desc *reg,
+		     unsigned long mmap_offset)
+{
+	int nr_pages, ret;
+	u64 end;
+
+	if (WARN_ON_ONCE(mr->pages || mr->ptr || mr->nr_pages))
+		return -EFAULT;
+	if (memchr_inv(&reg->__resv, 0, sizeof(reg->__resv)))
+		return -EINVAL;
+	if (reg->flags & ~IORING_MEM_REGION_TYPE_USER)
+		return -EINVAL;
+	/* user_addr should be set IFF it's a user memory backed region */
+	if ((reg->flags & IORING_MEM_REGION_TYPE_USER) != !!reg->user_addr)
+		return -EFAULT;
+	if (!reg->size || reg->mmap_offset || reg->id)
+		return -EINVAL;
+	if ((reg->size >> PAGE_SHIFT) > INT_MAX)
+		return -E2BIG;
+	if ((reg->user_addr | reg->size) & ~PAGE_MASK)
+		return -EINVAL;
+	if (check_add_overflow(reg->user_addr, reg->size, &end))
+		return -EOVERFLOW;
+
+	nr_pages = reg->size >> PAGE_SHIFT;
+	if (ctx->user) {
+		ret = __io_account_mem(ctx->user, nr_pages);
+		if (ret)
+			return ret;
+	}
+	mr->nr_pages = nr_pages;
+
+	if (reg->flags & IORING_MEM_REGION_TYPE_USER)
+		ret = io_region_pin_pages(mr, reg);
+	else
+		ret = io_region_allocate_pages(mr, reg, mmap_offset, ctx->user);
+	if (ret)
+		goto out_free;
+
+	ret = io_region_init_ptr(mr);
+	if (ret)
+		goto out_free;
+	return 0;
+out_free:
+	io_free_region(ctx->user, mr);
+	return ret;
+}
+
+static struct io_mapped_region *io_mmap_get_region(struct io_ring_ctx *ctx,
+						   loff_t pgoff)
+{
+	loff_t offset = pgoff << PAGE_SHIFT;
+	unsigned int id;
+
+
+	switch (offset & IORING_OFF_MMAP_MASK) {
+	case IORING_OFF_SQ_RING:
+	case IORING_OFF_CQ_RING:
+		return &ctx->ring_region;
+	case IORING_OFF_SQES:
+		return &ctx->sq_region;
+	case IORING_OFF_PBUF_RING:
+		id = (offset & ~IORING_OFF_MMAP_MASK) >> IORING_OFF_PBUF_SHIFT;
+		return io_pbuf_get_region(ctx, id);
+	case IORING_MAP_OFF_PARAM_REGION:
+		return &ctx->param_region;
+	case IORING_MAP_OFF_ZCRX_REGION:
+		id = (offset & ~IORING_OFF_MMAP_MASK) >> IORING_OFF_ZCRX_SHIFT;
+		return io_zcrx_get_region(ctx, id);
+	}
+	return NULL;
+}
+
+static void *io_region_validate_mmap(struct io_ring_ctx *ctx,
+				     struct io_mapped_region *mr)
+{
+	lockdep_assert_held(&ctx->mmap_lock);
+
+	if (!io_region_is_set(mr))
+		return ERR_PTR(-EINVAL);
+	if (mr->flags & IO_REGION_F_USER_PROVIDED)
+		return ERR_PTR(-EINVAL);
+
+	return io_region_get_ptr(mr);
+}
+
+static void *io_uring_validate_mmap_request(struct file *file, loff_t pgoff)
+{
+	struct io_ring_ctx *ctx = file->private_data;
+	struct io_mapped_region *region;
+
+	region = io_mmap_get_region(ctx, pgoff);
+	if (!region)
+		return ERR_PTR(-EINVAL);
+	return io_region_validate_mmap(ctx, region);
+}
+
+#ifdef CONFIG_MMU
+
+static int io_region_mmap(struct io_ring_ctx *ctx,
+			  struct io_mapped_region *mr,
+			  struct vm_area_struct *vma,
+			  unsigned max_pages)
+{
+	unsigned long nr_pages = min(mr->nr_pages, max_pages);
+
+	vm_flags_set(vma, VM_DONTEXPAND);
+	return vm_insert_pages(vma, vma->vm_start, mr->pages, &nr_pages);
+}
+
+__cold int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct io_ring_ctx *ctx = file->private_data;
+	size_t sz = vma->vm_end - vma->vm_start;
+	long offset = vma->vm_pgoff << PAGE_SHIFT;
+	unsigned int page_limit = UINT_MAX;
+	struct io_mapped_region *region;
+	void *ptr;
+
+	guard(mutex)(&ctx->mmap_lock);
+
+	ptr = io_uring_validate_mmap_request(file, vma->vm_pgoff);
+	if (IS_ERR(ptr))
+		return PTR_ERR(ptr);
+
+	switch (offset & IORING_OFF_MMAP_MASK) {
+	case IORING_OFF_SQ_RING:
+	case IORING_OFF_CQ_RING:
+		page_limit = (sz + PAGE_SIZE - 1) >> PAGE_SHIFT;
+		break;
+	}
+
+	region = io_mmap_get_region(ctx, vma->vm_pgoff);
+	return io_region_mmap(ctx, region, vma, page_limit);
+}
+
+unsigned long io_uring_get_unmapped_area(struct file *filp, unsigned long addr,
+					 unsigned long len, unsigned long pgoff,
+					 unsigned long flags)
+{
+	struct io_ring_ctx *ctx = filp->private_data;
+	void *ptr;
+
+	/*
+	 * Do not allow to map to user-provided address to avoid breaking the
+	 * aliasing rules. Userspace is not able to guess the offset address of
+	 * kernel kmalloc()ed memory area.
+	 */
+	if (addr)
+		return -EINVAL;
+
+	guard(mutex)(&ctx->mmap_lock);
+
+	ptr = io_uring_validate_mmap_request(filp, pgoff);
+	if (IS_ERR(ptr))
+		return PTR_ERR(ptr);
+
+	/*
+	 * Some architectures have strong cache aliasing requirements.
+	 * For such architectures we need a coherent mapping which aliases
+	 * kernel memory *and* userspace memory. To achieve that:
+	 * - use a NULL file pointer to reference physical memory, and
+	 * - use the kernel virtual address of the shared io_uring context
+	 *   (instead of the userspace-provided address, which has to be 0UL
+	 *   anyway).
+	 * - use the same pgoff which the get_unmapped_area() uses to
+	 *   calculate the page colouring.
+	 * For architectures without such aliasing requirements, the
+	 * architecture will return any suitable mapping because addr is 0.
+	 */
+	filp = NULL;
+	flags |= MAP_SHARED;
+	pgoff = 0;	/* has been translated to ptr above */
+#ifdef SHM_COLOUR
+	addr = (uintptr_t) ptr;
+	pgoff = addr >> PAGE_SHIFT;
+#else
+	addr = 0UL;
+#endif
+	return mm_get_unmapped_area(filp, addr, len, pgoff, flags);
+}
+
+#else /* !CONFIG_MMU */
+
+/*
+ * Drop the pages that were initially referenced and added in
+ * io_uring_mmap(). We cannot have had a mremap() as that isn't supported,
+ * hence the vma should be identical to the one we initially referenced and
+ * mapped, and partial unmaps and splitting isn't possible on a file backed
+ * mapping.
+ */
+static void io_uring_nommu_vm_close(struct vm_area_struct *vma)
+{
+	unsigned long index;
+
+	for (index = vma->vm_start; index < vma->vm_end; index += PAGE_SIZE)
+		put_page(virt_to_page((void *) index));
+}
+
+static const struct vm_operations_struct io_uring_nommu_vm_ops = {
+	.close = io_uring_nommu_vm_close,
+};
+
+int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct io_ring_ctx *ctx = file->private_data;
+	struct io_mapped_region *region;
+	unsigned long i;
+
+	if (!is_nommu_shared_mapping(vma->vm_flags))
+		return -EINVAL;
+
+	guard(mutex)(&ctx->mmap_lock);
+	region = io_mmap_get_region(ctx, vma->vm_pgoff);
+	if (!region || !io_region_is_set(region))
+		return -EINVAL;
+
+	if ((vma->vm_end - vma->vm_start) !=
+	    (unsigned long) region->nr_pages << PAGE_SHIFT)
+		return -EINVAL;
+
+	/*
+	 * Pin the pages so io_free_region()'s release_pages() does not
+	 * drop the last reference while this VMA exists. delete_vma()
+	 * in mm/nommu.c calls vma_close() which runs ->close above.
+	 */
+	for (i = 0; i < region->nr_pages; i++)
+		get_page(region->pages[i]);
+
+	vma->vm_ops = &io_uring_nommu_vm_ops;
+	return 0;
+}
+
+unsigned int io_uring_nommu_mmap_capabilities(struct file *file)
+{
+	return NOMMU_MAP_DIRECT | NOMMU_MAP_READ | NOMMU_MAP_WRITE;
+}
+
+unsigned long io_uring_get_unmapped_area(struct file *file, unsigned long addr,
+					 unsigned long len, unsigned long pgoff,
+					 unsigned long flags)
+{
+	struct io_ring_ctx *ctx = file->private_data;
+	void *ptr;
+
+	guard(mutex)(&ctx->mmap_lock);
+
+	ptr = io_uring_validate_mmap_request(file, pgoff);
+	if (IS_ERR(ptr))
+		return PTR_ERR(ptr);
+
+	return (unsigned long) ptr;
+}
+
+#endif /* !CONFIG_MMU */